Position statement: The case for a visualization performance benchmark

Abstract

Visualizations are an invaluable tool in the data analysis process, as they enable scientists to explore and interpret billions of datapoints quickly, and with just a few rendered images. However, many visualization systems are unable to keep up with the unprecedented accumulation of data through remote sensors, field sensors, medical and personal devices, social networks, and more. This is due to certain assumptions that many of these tools rely on, such as the assumption that these systems can store entire datasets directly in main memory. With so many datasets massive datasets available, ranging from the NASA MODIS satellite imagery dataset[3] to the Internet Movie Database [4] to Twitter streams [1], this assumption no longer matches reality.